{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:08:40Z","timestamp":1775200120124,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434732","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Text-Guided Speech Representations for Language Acquisition Assessment"],"prefix":"10.1109","author":[{"given":"Ilja","family":"Baumann","sequence":"first","affiliation":[{"name":"Technische Hochschule,Nürnberg"}]},{"given":"Dominik","family":"Wagner","sequence":"additional","affiliation":[{"name":"Technische Hochschule,Nürnberg"}]},{"given":"Philipp","family":"Seeberger","sequence":"additional","affiliation":[{"name":"Technische Hochschule,Nürnberg"}]},{"given":"Korbinian","family":"Riedhammer","sequence":"additional","affiliation":[{"name":"Technische Hochschule,Nürnberg"}]},{"given":"Tobias","family":"Bocklet","sequence":"additional","affiliation":[{"name":"Technische Hochschule,Nürnberg"}]}],"member":"263","reference":[{"key":"ref1","article-title":"SONAR: sentence-level multimodal and language-agnostic representations","author":"Duquenne","year":"2023","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096923"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3192714"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446635"},{"key":"ref5","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","volume":"abs\/2303.01037","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"issue":"97","key":"ref7","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref9","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201920","author":"Baevski"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2017-21"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2023-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2023-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10777"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2125"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3244393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389704"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101130"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-485"},{"key":"ref22","article-title":"Efficient few-shot learning without prompts","author":"Tunstall","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1055\/s-0035-1546898"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199571932.013.023"},{"key":"ref25","article-title":"Psycholinguistische analyse kindlicher aussprachest\u00f6rungen (plakss 2)","author":"Fox-Boyer","year":"2014"},{"key":"ref26","article-title":"Mpnet: masked and permuted pre-training for language understanding","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS \u201920.","author":"Song"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref30","first-page":"3475","article-title":"Panphon: A resource for mapping IPA segments to articulatory feature vectors","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. ACL","author":"Mortensen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-016-0455-0"},{"key":"ref32","article-title":"Kindliche aussprachest\u00f6rungen","volume":"7","author":"Fox-Boyer","year":"2016","journal-title":"Phonologischer Erwerb\u2013Differenzialdiagnostik\u2013Therapie"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-938"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref38","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"202. PMLR","author":"Radford"},{"key":"ref39","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref40","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434732.pdf?arnumber=11434732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:05Z","timestamp":1775192345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434732","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}